Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing the non-obvious state machine effect: adding images re-triggers AI moderation and pushes the listing back to 'pending', while removal does not. It also discloses cost ('free, no credit'), which the annotations cannot convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.